一篇新论文引入了一个新颖的框架，用于理解和推广宽神经网络中的正则化。研究发现，标准的岭正则化会扭曲特征学习网络的归纳偏置，尤其会影响预训练模型。为解决此问题，作者将一种与模型无关的规范正则化器公理化，并推导出了广义岭正则化，提出“arc ridge”作为一种实用、鲁棒的替代方法，它在不同学习模式下将早期停止与规范正则化联系起来。该理论通过图像处理和自然语言处理的实证研究得到了验证。 AI
影响 引入了一个新的理论框架，用于理解和改进神经网络训练，可能影响模型性能和泛化能力。
排序理由 该集群包含一篇详细介绍机器学习理论进展和实证验证的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2605.18180v1 Announce Type: new Abstract: Wide neural networks in the feature-learning regime drive modern deep learning, and yet they remain far less studied than their kernel-regime counterparts. We consider a critical yet under-explored difference between these two regim…
Wide neural networks in the feature-learning regime drive modern deep learning, and yet they remain far less studied than their kernel-regime counterparts. We consider a critical yet under-explored difference between these two regimes: the regulariser and prior implied by gradien…